The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in
response to a query. Although the most common formulation of text ranking is search …

Much of the evaluation and tuning of a search system relies on relevance labels---
annotations that say whether a document is useful for a given search and searcher. Ideally …

Retrieval and ranking models are the backbone of many applications such as web search,
open domain QA, or text-based recommender systems. The latency of neural ranking …

Recent years have witnessed a substantial increase in the use of deep learning to solve
various natural language processing (NLP) problems. Early deep learning models were …

Neural information retrieval systems typically use a cascading pipeline, in which a first-stage
model retrieves a candidate set of documents and one or more subsequent stages re-rank …

Pre-trained transformer models, such as BERT and T5, have shown to be highly effective at
ad hoc passage and document ranking. Due to the inherent sequence length limits of these …

Query expansion aims to mitigate the mismatch between the language used in a query and
in a document. However, query expansion methods can suffer from introducing non-relevant …

As information retrieval researchers, we not only develop algorithmic solutions to hard
problems, but we also insist on a proper, multifaceted evaluation of ideas. The literature on …

Societal biases resonate in the retrieved contents of information retrieval (IR) systems,
resulting in reinforcing existing stereotypes. Approaching this issue requires established …

Users of Web search engines reveal their information needs through queries and clicks,
making click logs a useful asset for information retrieval. However, click logs have not been …